检索结果-内蒙古大学图书馆

Data Driven control and Learning Systems (DDCLS)

作者： Mingwei Jia Danya Xu Tao Yang Yuan Yao Yi Liu Institute of Process Equipment and Control Engineering Zhejiang University of Technology Hangzhou State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang Department of Chemical Engineering National Tsing Hua University Taiwan

The development of an accurate soft sensor modeling method in the process industry remains a great challenge because the coupling relationship between variables is always intricate and difficult to model. In this work, a dynamic graph learning (DGL) soft sensor is proposed to alleviate this problem. The proposed model realizes the ability of the soft sensor to perceive the coupling relationship in real time by automatically learning the dynamic graph. Then, a causal convolutional mechanism and a multi-hop graph attention mechanism are used to systematically construct the dependencies of variables in the spatial-temporal dimension and model their variation patterns effectively. Finally, the proposed method is tested on the penicillin fermentation process and shown to be feasible and effective. The results showed that the change of the dynamic graph in the spatial-temporal dimension was in line with the process mechanism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent decision-making of shield tunneling machine using deep reinforcement learning in complex geological environment

引用

Engineering Applications of Artificial Intelligence 2025年 156卷

作者： Zhang, Wenshuai Liu, Xuanyu Zhang, Jiliang State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110004 China College of Information Science and Engineering Northeastern University Shenyang110004 China School of Information and Control Engineering Liaoning Petrochemical University Liaoning Fushun113001 China

To reduce constructional hazards of manual operation, the implementation an intelligent decision-making of the shield machine will be an inevitable development trend in the future. Hence, this paper suggests an intelligent decision-making approach using the Twin Delayed Deep Deterministic Policy Gradient (TD3) agent, which is constructed under the Actor-Critic framework. A robust nonlinear correlation exists between sealed cabin pressure and tunneling parameters. Therefore, a deep reinforcement learning (DRL) training environment is established using the sealed cabin pressure mechanism model. TD3 agent is trained by exploring empirical data obtained from continuous interactions between TD3 agent and the environment. Critic networks calculate the evaluation value of the action. TD3 selects the minimum evaluation value to avoid overestimating the parameters. Actor network adopts delayed updating parameters to make control process more stable and accurate. Based on earth theory model, target pressure values under different earth conditions are calculated. An appropriate reward function is established based on the target pressure for current soil conditions. TD3 agent dynamically adjusts the propulsion speed and screw conveyor speed in real-time according to geological environment to achieve intelligent control of the sealed cabin earth pressure. The experimental results show that the decision-making error of this method is 0 Megapascal (MPa), and it better adapts to random soil variations and can complete nearly a hundred different soil transition tasks in complex environments. This study promotes technological advancements in tunnel engineering by introducing artificial intelligence (AI) technology into tunnel construction field, realizing deep integration of AI technology and civil engineering. © 2025 Elsevier Ltd

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Dynamic Programming and Decentralized Optimal Output Regulation of Two-Time-Scale Interconnected Systems

Adaptive Dynamic Programming and Decentralized Optimal Outpu...

引用

International Conference on control, automation and Information Sciences (ICCAIS)

作者： Jianguo Zhao Chunyu Yang Linna Zhou Weinan Gao School of Information and Control Engineering China University of Mining and Technology Xuzhou China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

In this paper, we address the decentralized optimal output regulation problem for two-time-scale (TTS) interconnected systems with unknown slow dynamics through adaptive dynamic programming (ADP). Firstly, singular perturbation theory is leveraged to decompose the TTS interconnected system into a slow subsystem and several interconnected fast time-scale subsystems. Secondly, we develop a decentralized optimal control scheme for the fast time-scale subsystems with interconnections. Also, we devise an off-policy ADP algorithm to learn the optimal control strategy for the slow time-scale subsystem with unknown dynamics. Moreover, we combine the slow and fast control strategies to design the composite decentralized optimal output regulator. Both optimality and stability of the closed-loop system are rigorously analyzed. Finally, simulation results are provided to validate the effectiveness of the proposed methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Repetitive T-S Fuzzy Model-Based Iterative Learning control Law Design 63

Repetitive T-S Fuzzy Model-Based Iterative Learning Control ...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Maniarski, Robert Paszke, Wojciech Tao, Hongfeng Rogers, Eric Institute of Automation Electronic and Electrical Engineering University of Zielona Góra ul. Szafrana 2 Zielona Góra65-246 Poland Jiangnan University Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education Wuxi214000 China University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom

ISBN: (纸本)9798350316339

This paper develops an iterative learning control law for a class of nonlinear systems. The approach used to represent the nonlinear system dynamics is a Takagi-Sugeno fuzzy repetitive process that considers the two directions of information propagation. Then, the control action investigated is a state feedback control law combined with a PD-type feed-forward learning control law. Consequently, linear matrix inequality techniques can be used for control design. Furthermore, this approach allows the design of control action to satisfy the requirements on both the error convergence and the transient dynamics. Finally, an example demonstrates the properties of the new design. © 2024 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Addressing Domain Shift via Knowledge Space Sharing for Generalized Zero-Shot Industrial Fault Diagnosis

arXiv

引用

arXiv 2023年

作者： Zhao, Jiancheng Yue, Jiaqi Feng, Liangjun Zhao, Chunhui Ding, Jinliang College of Control Science and Engineering Zhejiang University Hangzhou310027 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

Fault diagnosis is a critical aspect of industrial safety, and supervised industrial fault diagnosis has been extensively researched. However, obtaining fault samples of all categories for model training can be challenging due to cost and safety concerns. As a result, the generalized zero-shot industrial fault diagnosis has gained attention as it aims to diagnose both seen and unseen faults. Nevertheless, the lack of unseen fault data for training poses a challenging domain shift problem (DSP), where unseen faults are often identified as seen faults. In this article, we propose a knowledge space sharing (KSS) model to address the DSP in the generalized zero-shot industrial fault diagnosis task. The KSS model includes a generation mechanism (KSS-G) and a discrimination mechanism (KSS-D). KSS-G generates samples for rare faults by recombining transferable attribute features extracted from seen samples under the guidance of auxiliary knowledge. KSS-D is trained in a supervised way with the help of generated samples, which aims to address the DSP by modeling seen categories in the knowledge space. KSS-D avoids misclassifying rare faults as seen faults and identifies seen fault samples. We conduct generalized zero-shot diagnosis experiments on the benchmark Tennessee-Eastman process, and our results show that our approach outperforms state-of-the-art methods for the generalized zero-shot industrial fault diagnosis problem. Note to Practitioners—This paper is motivated by the difficulty of fault diagnosis in practical industrial scenarios caused by the lack of fault samples for training supervised diagnosis models. The focus of this study is to develop a generalized zero-shot industrial fault diagnosis method, which can diagnose both faults with sufficient training samples and faults without training samples with the help of expert knowledge of these faults. Considering the generalized zero-shot diagnosis models often confuse unseen faults as seen faults, a knowledge spac

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Robust Stochastic Configuration Network Based Prediction Model of Total Nitrogen Content in Crude Oil

Robust Stochastic Configuration Network Based Prediction Mod...

引用

International Conference on Industrial Artificial Intelligence (IAI)

作者： Jun Lu Min Feng Jinliang Ding Xiaoling Zhang State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian University of Technology Dalian China

The refineries usually process the blending crude oil at present. Blending crude oil leads to the increased uncertainties of physical properties of crude oil. This paper presents a robust stochastic configuration network (SCN) based prediction model for total nitrogen content in crude oil. First, the robust SCN based on Bayesian framework is proposed. In the Bayesian framework, the noise and outliers are assumed to be the mixture of two Gaussian distributions to improve the robustness of SCN. Then, to solve the problem that there are no analytical solutions of parameters due to the assumption of mixture of Gaussian distributions, parameters of the proposed robust SCN are estimated by the expectation maximization (EM) algorithm. Experiments using the real-world data collected from a refinery are carried out. The results indicate that the proposed approach has better accuracy and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse Causality Analysis Approach with Time-varying Parameters for Root Cause Localization of Nonstationary process 4

Sparse Causality Analysis Approach with Time-varying Paramet...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Song, Pengyu Zhao, Chunhui Huang, Biao Ding, Jinliang College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China University of Alberta Department of Chemical and Materials Engineering EdmontonABT6G 2G6 Canada Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

Root cause diagnosis (RCD) is an important technique for maintaining the safe operation of industrial processes. Traditional RCD methods usually require stationarity assumptions. However, the process inevitably shows nonstationarity due to factors such as switching of operating conditions. Although there have been some previous studies trying to overcome the challenge of nonstationarity, these methods fail to guarantee the significance of the extracted causalities and lead to redundant relationships. To address the above issues, a sparse causal analysis model with time-varying parameters is extracted in this study. First, we propose an end-to-end information fusion and prediction task to characterize predictive relationships between variables and avoid repeated modeling. Second, we design time-varying parameters for the information fusion mechanism to cope with nonstationarity and automatically identify significant causality through sparse parameter updates. We design an update strategy that constrains the gradient information to guarantee sparsity. Finally, a causal metric is constructed for the time-varying predictive relationship to comprehensively obtain the overall causal relationship, which further guarantees causal significance. The validity of the proposed method is illustrated through a real industrial example collected from a thermal power plant. © 2022 IEEE.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Passivity-Based Online Reinforcement Learning for Real Time Model-Free Overhead Crane System control

Passivity-Based Online Reinforcement Learning for Real Time ...

引用

第34届中国控制与决策会议

作者： Haoran Zhang Chunhui Zhao Jinliang Ding State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

In this paper,a novel model-free online Reinforcement Learning(RL) control method is proposed for the real-time overhead crane control *** crane control problem is first formulated as an optimal regulation problem with a user-specified objective *** neural-networks,namely Actor-Critic networks,are employed to approximate the objective function and the optimal control policy ***,an improved network updating rule with an additional passivity-based stabilization term is developed to remove the requirement of the initial stabilizing control *** other crane control approaches,the proposed online RL algorithm does not rely on prior knowledge of the overhead crane mathematical ***,simulation studies are carried out to demonstrate the effectiveness of the proposed method in the presence of system parameter variations when compared to LQR control.

关键词： Overhead cranes Reinforcement Learning Q-learning Data-driven control

来源：评论

学校读者我要写书评

暂无评论

LBM modeling of three-dimensional mixed convection in CZ crystal growth on curvilinear coordinates system

引用

Results in Physics 2024年 61卷

作者： Zhang, Ni Liu, Ding The Department of Automation Xi'an Key Laboratory of Advanced Control and Intelligent Process Xi'an University of Posts and Telecommunications Xi'an 710121 China The Shaanxi Key Laboratory of Complex System Control and Intelligent of Information Processing Xi'an University of Technology Xi'an 710048 China

A three-dimensional (3D) thermal lattice Boltzmann model of crystal growth is presented to study the magneto-hydrodynamics (MHD) mixed convection in the melt of Czochralski silicon single crystal growth in this paper. In order to solve the problem of lattice Boltzmann method's difficulty in solving the flow of 3D cylindrical cavity, the 3D physical model of crystal growth is transformed from the Cartesian coordinate system to the Curvilinear coordinate system. And the irregular grids in the Cartesian coordinate system are transformed into regular grids in the Curvilinear coordinate system to facilitate the establishment of the Lattice Boltzmann model. Under the above operations, two coupled distribution functions are established to solve the governing equations. Two D3Q19 models are adopted to solve the melt velocity and temperature. And the 3D lattice Boltzmann modeling of crystal growth with cylinder boundary is realized by interpolation in Curvilinear coordinate system. The comparison with the experiment and other references proves that the proposed model and boundary treatment scheme is correct and it proposes a new way for studying the 3D crystal growth or other similar 3D cylindrical cavity simulations. Furthermore, the unstable melt flow for two cases are also simulated in this paper and the critical Reynolds number are also obtained. Results show that the introduction of the transverse magnetic field enhances the stability of the crystal growth system and increases the adjustable range of crystal rotation parameter. The obtained conclusion has an important reference for adjusting the process parameters during the CZ crystal growth. © 2024 The Author(s)

关键词： 3D mixed convection Computer simulation Heat transfer Lattice Boltzmann Method Silicon single crystal growth

来源：评论

学校读者我要写书评

暂无评论

Study on series voltage equalizing method of IGBT in high voltage circuits 3

Study on series voltage equalizing method of IGBT in high vo...

引用

3rd International Conference on Intelligent control, Measurement and Signal processing and Intelligent Oil Field, ICMSP 2021

作者： Yang, Jiahui Cao, Ke Li, Hong School of Electronic Engineering Xi'An Shiyou University Automation Instrument and Process Control Laboratory Xi an China Shannxi Gaoke Power Electronics Ltd Xi an China

ISBN: (纸本)9781665437158

In this paper, a gate $RC-\mathrm{D}$ voltage equalizer circuit is studied. The purpose of this circuit is to solve the problem that the emitter voltage distribution of each component set is uneven when IGBT runs in series. The working principle of gate $RC-\mathrm{D}$ voltage equalizer is described, and the functions of all components in the voltage equalizer are analyzed under different switching states of IGBT. Finally, a series voltage equalizer circuit model of IGBT is built on PSPICE platform for simulation. By comparing the simulation results of voltage equalizing circuit with or without voltage equalizing circuit, a good voltage equalizing effect is obtained after simulating voltage imbalance under 4000V DC voltage. It provides a guarantee condition for the stable operation of IGBT in series, thus verifying the feasibility of the scheme. © 2021 IEEE.

关键词： Insulated gate bipolar transistors (IGBT)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：